© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20225
    Prev
    Next
    INDEX
    Explanations

    time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to temporal phrases and questions regarding timing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.83
    ortment
    -0.76
    aking
    -0.73
    hid
    -0.68
    aughed
    -0.68
    edIn
    -0.68
    POR
    -0.67
    ruption
    -0.67
    kaya
    -0.66
    tyard
    -0.65
    POSITIVE LOGITS
     exactly
    1.15
    soever
    1.14
    abouts
    0.82
     someone
    0.76
    ce
    0.75
     they
    0.73
     somebody
    0.71
     prompted
    0.71
     else
    0.69
     quizz
    0.68
    Activations Density 0.080%

    No Known Activations